收藏切换
Railway accident entity extraction method based on accident phase classification and mutual learning
收藏切换
PDF
Zhibo Cheng, Yanhua Wu, Zheqian Liu, Yong Shi, Ze Li
Railway Sciences | 2025, 4(6) : 815 - 832
Less
收藏切换
Railway Sciences | 2025, 4(6): 815-832
Research article
Railway accident entity extraction method based on accident phase classification and mutual learning
Full
Zhibo Cheng, Yanhua Wu, Zheqian Liu, Yong Shi, Ze Li
Affiliations
  • China Academy of Railway Sciences Corporation Limited, Institute of Computing Technologies, Beijing, China
  • Safety Supervision and Management Bureau, China Railway Group Ltd, Beijing, China
  • China Academy of Railway Sciences Corporation Limited, Institute of Computing Technologies, Beijing, China
  • Zhibo Cheng is a researcher at China Academy of Railway Sciences Corporation Limited, specializing in research on railway big data analysis and safety data mining. She presided over or mainly participated in more than 20 scientific research projects, won 5 provincial and ministerial-level scientific and technological awards, and obtained 9 authorized national patents.

Published: 2025-12-10 doi: 10.1108/RS-08-2025-0030
Outline
收藏切换
Purpose

This study aims to enhance the accuracy of key entity extraction from railway accident report texts and address challenges such as complex domain-specific semantics, data sparsity and strong inter-sentence semantic dependencies. A robust entity extraction method tailored for accident texts is proposed.

Design/methodology/approach

This method is implemented through a dual-branch multi-task mutual learning model named R-MLP, which jointly performs entity recognition and accident phase classification. The model leverages a shared BERT encoder to extract contextual features and incorporates a sentence span indexing module to align feature granularity. A cross-task mutual learning mechanism is also introduced to strengthen semantic representation.

Findings

R-MLP effectively mitigates the impact of semantic complexity and data sparsity in domain entities and enhances the model's ability to capture inter-sentence semantic dependencies. Experimental results show that R-MLP achieves a maximum F1-score of 0.736 in extracting six types of key railway accident entities, significantly outperforming baseline models such as RoBERTa and MacBERT.

Originality/value

This demonstrates the proposed method's superior generalization and accuracy in domain-specific entity extraction tasks, confirming its effectiveness and practical value.

Accident report texts  /  Entity extraction  /  Accident phase classification  /  Multi-task model  /  Mutual learning mechanism
Zhibo Cheng, Yanhua Wu, Zheqian Liu, Yong Shi, Ze Li. Railway accident entity extraction method based on accident phase classification and mutual learning[J]. Railway Sciences, 2025 , 4 (6) : 815 -832 . DOI: 10.1108/RS-08-2025-0030
  • the Technology Research and Development Plan Program of China State Railway Group Co., Ltd.(Q2024T001)
  • the Foundation of China Academy of Railway Sciences Co., Ltd.(2024YJ259)
Year 2025 volume 4 Issue 6
PDF
9
0
Cite this Article
BibTeX
Article Info
doi: 10.1108/RS-08-2025-0030
  • Receive Date:2025-08-25
  • Online Date:2026-06-10
  • Published:2025-12-10
Article Data
Affiliations
History
  • Received:2025-08-25
  • Revised:2025-09-28
  • Accepted:2025-09-30
Funding
the Technology Research and Development Plan Program of China State Railway Group Co., Ltd.(Q2024T001)
the Foundation of China Academy of Railway Sciences Co., Ltd.(2024YJ259)
Affiliations
    China Academy of Railway Sciences Corporation Limited, Institute of Computing Technologies, Beijing, China
    Safety Supervision and Management Bureau, China Railway Group Ltd, Beijing, China
    China Academy of Railway Sciences Corporation Limited, Institute of Computing Technologies, Beijing, China

Corresponding:

Zhibo Cheng can be contacted at:
References
Share
https://castjournals.cast.org.cn/joweb/rs/EN/10.1108/RS-08-2025-0030
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT